from sklearn.metrics import confusion_matrix,accuracy_score,recall_score,precision_score,f1_score,fbeta_score,classification_report
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC
import seaborn as sns
import pandas as pd
import numpy as np
import sklearn
import matplotlib
import matplotlib.pyplot as plt
import plotly.express as px

df = pd.read_csv(r'C:\Users\lenovo\Downloads\heart_disease_health_indicators.csv')

Data cleaning

df.shape

(253680, 22)

df.head()

	HeartDiseaseorAttack	HighBP	HighChol	CholCheck	BMI	Smoker	Stroke	Diabetes	PhysActivity	Fruits	...	AnyHealthcare	NoDocbcCost	GenHlth	MentHlth	PhysHlth	DiffWalk	Sex	Age	Education	Income
0	0.0	1.0	1.0	1.0	40.0	1.0	0.0	0.0	0.0	0.0	...	1.0	0.0	5.0	18.0	15.0	1.0	0.0	9.0	4.0	3.0
1	0.0	0.0	0.0	0.0	25.0	1.0	0.0	0.0	1.0	0.0	...	0.0	1.0	3.0	0.0	0.0	0.0	0.0	7.0	6.0	1.0
2	0.0	1.0	1.0	1.0	28.0	0.0	0.0	0.0	0.0	1.0	...	1.0	1.0	5.0	30.0	30.0	1.0	0.0	9.0	4.0	8.0
3	0.0	1.0	0.0	1.0	27.0	0.0	0.0	0.0	1.0	1.0	...	1.0	0.0	2.0	0.0	0.0	0.0	0.0	11.0	3.0	6.0
4	0.0	1.0	1.0	1.0	24.0	0.0	0.0	0.0	1.0	1.0	...	1.0	0.0	2.0	3.0	0.0	0.0	0.0	11.0	5.0	4.0

5 rows × 22 columns

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 253680 entries, 0 to 253679
Data columns (total 22 columns):
 #   Column                Non-Null Count   Dtype  
---  ------                --------------   -----  
 0   HeartDiseaseorAttack  253680 non-null  float64
 1   HighBP                253680 non-null  float64
 2   HighChol              253680 non-null  float64
 3   CholCheck             253680 non-null  float64
 4   BMI                   253680 non-null  float64
 5   Smoker                253680 non-null  float64
 6   Stroke                253680 non-null  float64
 7   Diabetes              253680 non-null  float64
 8   PhysActivity          253680 non-null  float64
 9   Fruits                253680 non-null  float64
 10  Veggies               253680 non-null  float64
 11  HvyAlcoholConsump     253680 non-null  float64
 12  AnyHealthcare         253680 non-null  float64
 13  NoDocbcCost           253680 non-null  float64
 14  GenHlth               253680 non-null  float64
 15  MentHlth              253680 non-null  float64
 16  PhysHlth              253680 non-null  float64
 17  DiffWalk              253680 non-null  float64
 18  Sex                   253680 non-null  float64
 19  Age                   253680 non-null  float64
 20  Education             253680 non-null  float64
 21  Income                253680 non-null  float64
dtypes: float64(22)
memory usage: 42.6 MB

df.describe()

	HeartDiseaseorAttack	HighBP	HighChol	CholCheck	BMI	Smoker	Stroke	Diabetes	PhysActivity	Fruits	...	AnyHealthcare	NoDocbcCost	GenHlth	MentHlth	PhysHlth	DiffWalk	Sex	Age	Education	Income
count	253680.000000	253680.000000	253680.000000	253680.000000	253680.000000	253680.000000	253680.000000	253680.000000	253680.000000	253680.000000	...	253680.000000	253680.000000	253680.000000	253680.000000	253680.000000	253680.000000	253680.000000	253680.000000	253680.000000	253680.000000
mean	0.094186	0.429001	0.424121	0.962670	28.382364	0.443169	0.040571	0.296921	0.756544	0.634256	...	0.951053	0.084177	2.511392	3.184772	4.242081	0.168224	0.440342	8.032119	5.050434	6.053875
std	0.292087	0.494934	0.494210	0.189571	6.608694	0.496761	0.197294	0.698160	0.429169	0.481639	...	0.215759	0.277654	1.068477	7.412847	8.717951	0.374066	0.496429	3.054220	0.985774	2.071148
min	0.000000	0.000000	0.000000	0.000000	12.000000	0.000000	0.000000	0.000000	0.000000	0.000000	...	0.000000	0.000000	1.000000	0.000000	0.000000	0.000000	0.000000	1.000000	1.000000	1.000000
25%	0.000000	0.000000	0.000000	1.000000	24.000000	0.000000	0.000000	0.000000	1.000000	0.000000	...	1.000000	0.000000	2.000000	0.000000	0.000000	0.000000	0.000000	6.000000	4.000000	5.000000
50%	0.000000	0.000000	0.000000	1.000000	27.000000	0.000000	0.000000	0.000000	1.000000	1.000000	...	1.000000	0.000000	2.000000	0.000000	0.000000	0.000000	0.000000	8.000000	5.000000	7.000000
75%	0.000000	1.000000	1.000000	1.000000	31.000000	1.000000	0.000000	0.000000	1.000000	1.000000	...	1.000000	0.000000	3.000000	2.000000	3.000000	0.000000	1.000000	10.000000	6.000000	8.000000
max	1.000000	1.000000	1.000000	1.000000	98.000000	1.000000	1.000000	2.000000	1.000000	1.000000	...	1.000000	1.000000	5.000000	30.000000	30.000000	1.000000	1.000000	13.000000	6.000000	8.000000

8 rows × 22 columns

df.isnull().sum()

HeartDiseaseorAttack    0
HighBP                  0
HighChol                0
CholCheck               0
BMI                     0
Smoker                  0
Stroke                  0
Diabetes                0
PhysActivity            0
Fruits                  0
Veggies                 0
HvyAlcoholConsump       0
AnyHealthcare           0
NoDocbcCost             0
GenHlth                 0
MentHlth                0
PhysHlth                0
DiffWalk                0
Sex                     0
Age                     0
Education               0
Income                  0
dtype: int64

df.duplicated().sum()

23899

df.drop_duplicates(inplace = True)

df.duplicated().sum()

0

df.shape

(229781, 22)

df['Age'] = df['Age']*4
df

	HeartDiseaseorAttack	HighBP	HighChol	CholCheck	BMI	Smoker	Stroke	Diabetes	PhysActivity	Fruits	...	AnyHealthcare	NoDocbcCost	GenHlth	MentHlth	PhysHlth	DiffWalk	Sex	Age	Education	Income
0	0.0	1.0	1.0	1.0	40.0	1.0	0.0	0.0	0.0	0.0	...	1.0	0.0	5.0	18.0	15.0	1.0	0.0	36.0	4.0	3.0
1	0.0	0.0	0.0	0.0	25.0	1.0	0.0	0.0	1.0	0.0	...	0.0	1.0	3.0	0.0	0.0	0.0	0.0	28.0	6.0	1.0
2	0.0	1.0	1.0	1.0	28.0	0.0	0.0	0.0	0.0	1.0	...	1.0	1.0	5.0	30.0	30.0	1.0	0.0	36.0	4.0	8.0
3	0.0	1.0	0.0	1.0	27.0	0.0	0.0	0.0	1.0	1.0	...	1.0	0.0	2.0	0.0	0.0	0.0	0.0	44.0	3.0	6.0
4	0.0	1.0	1.0	1.0	24.0	0.0	0.0	0.0	1.0	1.0	...	1.0	0.0	2.0	3.0	0.0	0.0	0.0	44.0	5.0	4.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
253675	0.0	1.0	1.0	1.0	45.0	0.0	0.0	0.0	0.0	1.0	...	1.0	0.0	3.0	0.0	5.0	0.0	1.0	20.0	6.0	7.0
253676	0.0	1.0	1.0	1.0	18.0	0.0	0.0	2.0	0.0	0.0	...	1.0	0.0	4.0	0.0	0.0	1.0	0.0	44.0	2.0	4.0
253677	0.0	0.0	0.0	1.0	28.0	0.0	0.0	0.0	1.0	1.0	...	1.0	0.0	1.0	0.0	0.0	0.0	0.0	8.0	5.0	2.0
253678	0.0	1.0	0.0	1.0	23.0	0.0	0.0	0.0	0.0	1.0	...	1.0	0.0	3.0	0.0	0.0	0.0	1.0	28.0	5.0	1.0
253679	1.0	1.0	1.0	1.0	25.0	0.0	0.0	2.0	1.0	1.0	...	1.0	0.0	2.0	0.0	0.0	0.0	0.0	36.0	6.0	2.0

229781 rows × 22 columns

df['Age'].max()

52.0

df['Age'].min()

4.0

df["HeartDiseaseorAttack"].value_counts() 

0.0    206064
1.0     23717
Name: HeartDiseaseorAttack, dtype: int64

df.columns

Index(['HeartDiseaseorAttack', 'HighBP', 'HighChol', 'CholCheck', 'BMI',
       'Smoker', 'Stroke', 'Diabetes', 'PhysActivity', 'Fruits', 'Veggies',
       'HvyAlcoholConsump', 'AnyHealthcare', 'NoDocbcCost', 'GenHlth',
       'MentHlth', 'PhysHlth', 'DiffWalk', 'Sex', 'Age', 'Education',
       'Income'],
      dtype='object')

Describe the dataset attributes

HeartDiseaseorAttack: A binary variable indicating whether the individual has a history of heart disease or heart attack. HighBP: A binary variable indicating whether the individual has high blood pressure. HighChol: A binary variable indicating whether the individual has high cholesterol. CholCheck: A binary variable indicating whether the individual has had their cholesterol checked. BMI: A continuous variable representing the individual's body mass index, which is a measure of body fat based on height and weight. Smoker: A binary variable indicating whether the individual smokes cigarettes or not. Stroke: A binary variable indicating whether the individual has had a stroke. Diabetes: A binary variable indicating whether the individual has diabetes. PhysActivity: A categorical variable indicating the level of physical activity of the individual. Fruits: A continuous variable representing the number of servings of fruits the individual consumes. Veggies: A continuous variable representing the number of servings of vegetables the individual consumes. HvyAlcoholConsump: A binary variable indicating whether the individual has heavy alcohol consumption. AnyHealthcare: A binary variable indicating whether the individual has any healthcare coverage. NoDocbcCost: A binary variable indicating whether the individual does not have any doctor's visits due to cost. GenHlth: A categorical variable indicating the general health status of the individual. MentHlth: A categorical variable indicating the mental health status of the individual. PhysHlth: A continuous variable representing the number of days the individual's physical health was not good. DiffWalk: A binary variable indicating whether the individual has difficulty walking. Sex: A categorical variable indicating the gender of the individual. Age: A continuous variable representing the age of the individual. Education: A categorical variable indicating the highest level of education completed by the individual. Income: A categorical variable indicating the income level of the individual.

print("no. of column = ", len(df.columns))

no. of column =  22

df1 = df.drop([ 'Education', 'Income'], axis=1)
df1

	HeartDiseaseorAttack	HighBP	HighChol	CholCheck	BMI	Smoker	Stroke	Diabetes	PhysActivity	Fruits	Veggies	HvyAlcoholConsump	AnyHealthcare	NoDocbcCost	GenHlth	MentHlth	PhysHlth	DiffWalk	Sex	Age
0	0.0	1.0	1.0	1.0	40.0	1.0	0.0	0.0	0.0	0.0	1.0	0.0	1.0	0.0	5.0	18.0	15.0	1.0	0.0	36.0
1	0.0	0.0	0.0	0.0	25.0	1.0	0.0	0.0	1.0	0.0	0.0	0.0	0.0	1.0	3.0	0.0	0.0	0.0	0.0	28.0
2	0.0	1.0	1.0	1.0	28.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0	1.0	1.0	5.0	30.0	30.0	1.0	0.0	36.0
3	0.0	1.0	0.0	1.0	27.0	0.0	0.0	0.0	1.0	1.0	1.0	0.0	1.0	0.0	2.0	0.0	0.0	0.0	0.0	44.0
4	0.0	1.0	1.0	1.0	24.0	0.0	0.0	0.0	1.0	1.0	1.0	0.0	1.0	0.0	2.0	3.0	0.0	0.0	0.0	44.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
253675	0.0	1.0	1.0	1.0	45.0	0.0	0.0	0.0	0.0	1.0	1.0	0.0	1.0	0.0	3.0	0.0	5.0	0.0	1.0	20.0
253676	0.0	1.0	1.0	1.0	18.0	0.0	0.0	2.0	0.0	0.0	0.0	0.0	1.0	0.0	4.0	0.0	0.0	1.0	0.0	44.0
253677	0.0	0.0	0.0	1.0	28.0	0.0	0.0	0.0	1.0	1.0	0.0	0.0	1.0	0.0	1.0	0.0	0.0	0.0	0.0	8.0
253678	0.0	1.0	0.0	1.0	23.0	0.0	0.0	0.0	0.0	1.0	1.0	0.0	1.0	0.0	3.0	0.0	0.0	0.0	1.0	28.0
253679	1.0	1.0	1.0	1.0	25.0	0.0	0.0	2.0	1.0	1.0	0.0	0.0	1.0	0.0	2.0	0.0	0.0	0.0	0.0	36.0

229781 rows × 20 columns

Data Exploration & visualization

correlation = df1.corr()  
#correlation.style.background_gradient(cmap = 'BrBG')  
plt.figure(figsize = (8,8))
sns.heatmap(correlation, cbar=True, square=True, fmt='.1f',annot=True, annot_kws={'size':8}, cmap='Purples')

<AxesSubplot:>

#The interquartile range (IQR) is a measure of statistical dispersion,prints the IQR scores, which can be used to detect outliers.
Q1 = df1.quantile(0.25)
Q3 = df1.quantile(0.75)
IQR = Q3 - Q1
print(IQR)

HeartDiseaseorAttack     0.0
HighBP                   1.0
HighChol                 1.0
CholCheck                0.0
BMI                      8.0
Smoker                   1.0
Stroke                   0.0
Diabetes                 0.0
PhysActivity             1.0
Fruits                   1.0
Veggies                  0.0
HvyAlcoholConsump        0.0
AnyHealthcare            0.0
NoDocbcCost              0.0
GenHlth                  1.0
MentHlth                 2.0
PhysHlth                 4.0
DiffWalk                 0.0
Sex                      1.0
Age                     16.0
dtype: float64

# Create a figure and axis
fig, ax = plt.subplots(figsize=(75, 30))

# Plot the box plots for all columns
df1.boxplot(ax=ax)
plt.ylim(bottom=0, top=2500)
# Show the plot
plt.show()

sns.boxplot(df1['BMI'])

C:\Users\lenovo\anaconda3\lib\site-packages\seaborn\_decorators.py:36: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(

<AxesSubplot:xlabel='BMI'>

sns.boxplot(df1['PhysHlth'])

C:\Users\lenovo\anaconda3\lib\site-packages\seaborn\_decorators.py:36: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(

<AxesSubplot:xlabel='PhysHlth'>

data = [df1["HeartDiseaseorAttack"], df1["Age"], df1["BMI"], df1["PhysHlth"]]
 
fig = plt.figure(figsize =(10, 7))
ax = fig.add_subplot(111)
 
# Creating axes instance
bp = ax.boxplot(data, patch_artist = True,
                notch ='True', vert = 0)
 
colors = ['#0000FF', '#00FF00',
          '#FFFF00', '#FF00FF']
 
for patch, color in zip(bp['boxes'], colors):
    patch.set_facecolor(color)
 
# changing color and linewidth of
# whiskers
for whisker in bp['whiskers']:
    whisker.set(color ='#8B008B',
                linewidth = 1.5,
                linestyle =":")
 
# changing color and linewidth of
# caps
for cap in bp['caps']:
    cap.set(color ='#8B008B',
            linewidth = 2)
 
# changing color and linewidth of
# medians
for median in bp['medians']:
    median.set(color ='red',
               linewidth = 3)
 
# changing style of fliers
for flier in bp['fliers']:
    flier.set(marker ='D',
              color ='#e7298a',
              alpha = 0.5)
     
# x-axis labels
ax.set_yticklabels(['HeartDiseaseorAttack', 'Age',
                    'BMI', 'PhysHlth'])
 
# Adding title
plt.title("Customized box plot")
 
# Removing top axes and right axes
# ticks
ax.get_xaxis().tick_bottom()
ax.get_yaxis().tick_left()
     
# show plot
plt.show()

df2 = df1[~((df1 < (Q1 - 1.5 * IQR)) |(df1 > (Q3 + 1.5 * IQR))).any(axis=1)]
print(df2.shape)

(79138, 20)

x=['HeartDiseaseorAttack','Age','HighChol','Diabetes','HighBP', 'Fruits','Smoker']
for i in x :
    fig = px.histogram(df1, x=df1[i], nbins=50)
    fig.show()

sns.pairplot(df1)

<seaborn.axisgrid.PairGrid at 0x21125850610>

sns.countplot(x='Sex', data=df1, hue='Smoker')

<AxesSubplot:xlabel='Sex', ylabel='count'>

sns.countplot(x='Smoker', data=df1, hue='HeartDiseaseorAttack')

<AxesSubplot:xlabel='Smoker', ylabel='count'>

#Make a countplot on the features to differentiate them into binary, categorical and numerical features
# Countplot on each feature
plt.figure(figsize=(20,60))
for i,column in enumerate(df1.columns):
    plt.subplot(len(df1.columns), 5, i+1)
    plt.suptitle("Plot Value Count", fontsize=20, x=0.5, y=1)
    sns.countplot(data=df1, x=column)
    plt.title(f"{column}")
    plt.tight_layout()

# Separate into target, binary, categorical and numerical features
target = ['HeartDiseaseorAttack']
bin_features = ['HighBP', 'HighChol', 'CholCheck','Smoker', 'Stroke','PhysActivity', 'Fruits', 'Veggies', 
                'HvyAlcoholConsump', 'AnyHealthcare', 'NoDocbcCost', 'DiffWalk', 'Sex']
cat_features = ['Diabetes', 'GenHlth']
num_features = ['BMI','MentHlth', 'PhysHlth', 'Age']

# Explore distribtuion of binary features with pie charts
plt.figure(figsize=(20,60))
for i,column in enumerate(bin_features):
        plt.subplot(len(bin_features), 5, i+1)
        plt.pie(x=df1[column].value_counts(), labels=df1[column].unique(), autopct='%.0f%%')
        plt.title(f"{column}")
        plt.tight_layout()

# Explore distribtuion of numerical features histograms
fig, axes = plt.subplots(2, 2, figsize=(18, 10))
sns.histplot(ax=axes[0,0], data=df1, x=num_features[0])
sns.histplot(ax=axes[0,1], data=df1, x=num_features[1])
sns.histplot(ax=axes[1,0], data=df1, x=num_features[2])
sns.histplot(ax=axes[1,1], data=df1, x=num_features[3])

<AxesSubplot:xlabel='Age', ylabel='Count'>

sns.distplot(df1['Age'], kde=False, color='purple')

C:\Users\lenovo\anaconda3\lib\site-packages\seaborn\distributions.py:2619: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)

<AxesSubplot:xlabel='Age'>

sns.distplot(df2['BMI'], kde=False)

C:\Users\lenovo\anaconda3\lib\site-packages\seaborn\distributions.py:2619: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms).
  warnings.warn(msg, FutureWarning)

<AxesSubplot:xlabel='BMI'>

#the relation between Body mass and heart Diseases and if body mass can affect on person with making
#it possible to have heart Diseases or any other Diseases or not
sns.countplot(x='BMI', data=df1, hue='HeartDiseaseorAttack')

<AxesSubplot:xlabel='BMI', ylabel='count'>

sns.countplot(x='BMI', data=df1, hue='Diabetes')

<AxesSubplot:xlabel='BMI', ylabel='count'>

#how healthcare is so important and how it affect on person and make him good more than people who don't have
sns.countplot(x='AnyHealthcare', data=df1, hue='HeartDiseaseorAttack')

<AxesSubplot:xlabel='AnyHealthcare', ylabel='count'>

sns.countplot(x='AnyHealthcare', data=df1, hue='Diabetes')

<AxesSubplot:xlabel='AnyHealthcare', ylabel='count'>

Model building & Normalization

x=df1.drop(['HeartDiseaseorAttack'], axis=1)
y=df1['HeartDiseaseorAttack']

x_train, x_test, y_train, y_test =  train_test_split( x , y ,test_size=0.3)
y_train.value_counts()

0.0    144296
1.0     16550
Name: HeartDiseaseorAttack, dtype: int64

from sklearn.preprocessing import StandardScaler
scaler=StandardScaler()

x_train=scaler.fit_transform(x_train)
x_test=scaler.transform(x_test)

models={
    'LR':LogisticRegression(),
    'KNN':KNeighborsClassifier(),
    'DT':DecisionTreeClassifier(),
    'SVC':SVC(),
    'NB':GaussianNB(),
    'RF':RandomForestClassifier()
    
}

for name,model in  models.items():
    print(f'using {name}: ')
    model.fit(x_train,y_train)
    y_pred=model.predict(x_test)
    print(f'Training Accuracy :{accuracy_score(y_train,model.predict(x_train))}')
    print(f'Testing Accuracy :{accuracy_score(y_test,y_pred)}')
    print(f'Confusion matrix:\n {confusion_matrix(y_test,y_pred)}')
    print(f'Recall: {recall_score(y_test,y_pred)}')
    print(f'precision: {precision_score(y_test,y_pred)}')
    print(f'F1-score: {f1_score(y_test,y_pred)}')
    print(f'Fbeta-score: {fbeta_score(y_test,y_pred,beta=0.5)}')
    print(classification_report(y_test,y_pred))
    print('-'*33)

using LR: 
Training Accuracy :0.8988535617920247
Testing Accuracy :0.8987161819104954
Confusion matrix:
 [[61081   687]
 [ 6295   872]]
Recall: 0.12166875959257709
precision: 0.5593329057087877
F1-score: 0.19986247994499198
Fbeta-score: 0.3253003059016637
              precision    recall  f1-score   support

         0.0       0.91      0.99      0.95     61768
         1.0       0.56      0.12      0.20      7167

    accuracy                           0.90     68935
   macro avg       0.73      0.56      0.57     68935
weighted avg       0.87      0.90      0.87     68935

---------------------------------
using KNN: 
Training Accuracy :0.9113748554517986
Testing Accuracy :0.8853267570900123
Confusion matrix:
 [[59904  1864]
 [ 6041  1126]]
Recall: 0.157108971675736
precision: 0.3765886287625418
F1-score: 0.22171901151914933
Fbeta-score: 0.29434830344539137
              precision    recall  f1-score   support

         0.0       0.91      0.97      0.94     61768
         1.0       0.38      0.16      0.22      7167

    accuracy                           0.89     68935
   macro avg       0.64      0.56      0.58     68935
weighted avg       0.85      0.89      0.86     68935

---------------------------------
using DT: 
Training Accuracy :0.9861482411747883
Testing Accuracy :0.844215565387684
Confusion matrix:
 [[56364  5404]
 [ 5335  1832]]
Recall: 0.25561601785963445
precision: 0.2531785516860144
F1-score: 0.25439144622648063
Fbeta-score: 0.2536623189609814
              precision    recall  f1-score   support

         0.0       0.91      0.91      0.91     61768
         1.0       0.25      0.26      0.25      7167

    accuracy                           0.84     68935
   macro avg       0.58      0.58      0.58     68935
weighted avg       0.84      0.84      0.84     68935

---------------------------------
using SVC: 
Training Accuracy :0.9011041617447745
Testing Accuracy :0.8979183288605208
Confusion matrix:
 [[61510   258]
 [ 6779   388]]
Recall: 0.05413701688293568
precision: 0.6006191950464397
F1-score: 0.09932164341482146
Fbeta-score: 0.19895395344067274
              precision    recall  f1-score   support

         0.0       0.90      1.00      0.95     61768
         1.0       0.60      0.05      0.10      7167

    accuracy                           0.90     68935
   macro avg       0.75      0.52      0.52     68935
weighted avg       0.87      0.90      0.86     68935

---------------------------------
using NB: 
Training Accuracy :0.8110739465078398
Testing Accuracy :0.81231594980779
Confusion matrix:
 [[52141  9627]
 [ 3311  3856]]
Recall: 0.5380214873726803
precision: 0.28598976488911965
F1-score: 0.3734624697336562
Fbeta-score: 0.3155534460465801
              precision    recall  f1-score   support

         0.0       0.94      0.84      0.89     61768
         1.0       0.29      0.54      0.37      7167

    accuracy                           0.81     68935
   macro avg       0.61      0.69      0.63     68935
weighted avg       0.87      0.81      0.84     68935

---------------------------------
using RF: 
Training Accuracy :0.9860860699053753
Testing Accuracy :0.8861246101399869
Confusion matrix:
 [[60097  1671]
 [ 6179   988]]
Recall: 0.1378540532998465
precision: 0.37156825874388866
F1-score: 0.20109912477101569
Fbeta-score: 0.2774813233724653
              precision    recall  f1-score   support

         0.0       0.91      0.97      0.94     61768
         1.0       0.37      0.14      0.20      7167

    accuracy                           0.89     68935
   macro avg       0.64      0.56      0.57     68935
weighted avg       0.85      0.89      0.86     68935

---------------------------------

Histograms: To visualize the distribution of continuous features such as age. Box plots: To visualize the distribution and spread of continuous features and detect outliers. Bar plots: To visualize the frequency distribution of categorical features such as education. Heatmaps: To visualize the correlation matrix between different features. Scatter plots: To observe relationships between variables and uses dots to represent the relationship between them. countplot: To method is used to Show the counts of observations in each categorical bin using bars.